@Saccc_c: Discovered an animation generation tool that directly converts natural language into cool Lottie animations. The effects shown in the video below can be generated in one go — very impressive. (The prompt guide is in the comments, you can feed it directly to AI to help write high-quality prompts.) Combining it with video production tools like HyperFrames opens up even more possibilities. Finally...
Summary
An open-source tool that uses AI agents (such as Claude Code/Codex) to directly convert natural language into production-ready Lottie animations, supporting one-click installation and a prompt guide.
View Cached Full Text
Cached at: 06/12/26, 10:58 AM
Discovered an animation generation tool that directly converts natural language into stunning Lottie animations. The effects shown in the video below can be generated in one go—it’s incredibly impressive. (The prompt guide is in the comments; you can feed it to AI to help write high-quality prompts for you.) Combining it with video production tools like HyperFrames opens up even more possibilities. Install it from the terminal with one command: $ npx skills add diffusionstudio/lottie Repository link: https://github.com/diffusionstudio/lottie
diffusionstudio/lottie
Source: https://github.com/diffusionstudio/lottie
Text-to-lottie is an open-source harness for generating production ready Lottie animations with claude code/codex or any other coding agent supporting skills.
Created with Text-to-Lottie
Quick Start
Install the skill:
npx skills add diffusionstudio/lottie
Then ask your coding agent to generate a Lottie animation using text-to-lottie. Example prompt:
Create a Lottie animation from the SVG path in https://github.com/JaceThings/SF-Hello/blob/main/SVG/hello-en.svg. Reveal the path with an animation that follows the natural path direction. Apply a premium apple themed gradient to the path. Use ease-in-out timing, a transparent background, and preserve the original SVG geometry.
The agent will setup a harness that allows you to inspect/edit the generated lottie with the included player.
Prompt guide
1. Ground the model
Provide SVGs, real-world data, or screenshots whenever possible. Results are significantly better when the animation is based on concrete assets.
2. Use motion design terminology
Describe timing and movement using motion design language like ease-in, ease-out, and ease-in-out.
3. Think like a camera operator
Professional motion graphics often rely on camera movement. Include camera pushes, pans, zooms, and rig-like motion in your prompt. The agent can simulate these through group transforms.
4. Request the controls you need
By default, outputs usually only expose a background color control. If you want to customize other properties, explicitly ask the agent to create controls for them.
5. Specify FPS and duration
If your animation requires a specific frame rate or length, include the desired FPS and total frame count in the prompt.
Using the Generated Animation
Generated animations can be used directly as Lottie JSON files or imported into After Effects for further refinement.
Web / vanilla HTML
lottie.loadAnimation({
container: document.getElementById("anim"),
renderer: "svg",
loop: true,
autoplay: true,
path: "/animations/my-animation.json"
});
React Native
import LottieView from "lottie-react-native";
export default function Loader() {
return (
<LottieView
source={require("./animation.json")}
autoPlay
loop
/>
);
}
Alternatively, React Native Skia (https://shopify.github.io/react-native-skia/docs/skottie/) can also render Lottie animations via its Skottie module, including on the web. It lets you customize animation properties, assets, and typographies at runtime, and since Skottie is a regular Skia drawing, it can be composed into a larger Skia scene alongside shaders, effects, and masks.
import { Skia, Canvas, Skottie, useClock } from "@shopify/react-native-skia";
import { useDerivedValue } from "react-native-reanimated";
const animation = Skia.Skottie.Make(JSON.stringify(require("./animation.json")));
export default function Loader() {
const clock = useClock();
const frame = useDerivedValue(
() => ((clock.value / 1000) % animation.duration()) * animation.fps()
);
return (
<Canvas style={{ flex: 1 }}>
<Skottie animation={animation} frame={frame} />
</Canvas>
);
}
iOS Swift
import Lottie
let animationView = LottieAnimationView(name: "animation")
animationView.frame = view.bounds
animationView.contentMode = .scaleAspectFit
animationView.loopMode = .loop
view.addSubview(animationView)
animationView.play()
Android Kotlin
val view = findViewById(R.id.animationView)
view.setAnimation(R.raw.animation)
view.loop(true)
view.playAnimation()
Flutter
dependencies:
lottie: ^latest
import 'package:lottie/lottie.dart';
Lottie.asset('assets/animation.json')
Sac (@Saccc_c):
If you had bought $200,000 worth of Nvidia at its 2009 low, you’d be a billionaire today.
Used HyperFrames + Lottie skill to make this Nvidia stock price retrospective video.
Similar Articles
@Saccc_c: If you want AI to create professional-grade animations, you first need to learn how to describe them. Linear design engineer Emil Kowalski compiled 90+ animation terms, covering 12 categories including elastic animations, interaction feedback, etc. Useful for websites and video animations. http://animations.d…
Linear design engineer Emil Kowalski compiled over 90 animation terms across 12 categories to help users better describe animation effects to AI. Additionally, the author used Claude to build a bilingual preview site to facilitate understanding of each term's actual effect.
@yhslgg: Old Yang shares another gem open-source tool—KrillinAI, 10,000 stars on GitHub, a must-see for multilingual audio/video content! In a nutshell: from video download to subtitle translation, AI dubbing, video compositing, the entire pipeline is covered, and it can even auto-generate platform covers, supporting Bilibili, Douyin, Xiaohongshu, YouTube…
KrillinAI is an open-source tool that integrates the entire workflow of video downloading, subtitle translation, AI dubbing, and video compositing. It supports context-aware translation, voice cloning, auto layout, and cover generation, and is compatible with multiple AI models, suitable for multilingual audio/video content creation and distribution.
@zhouluobo: Not hiding anymore, folks. I've turned the recent super popular FPV video gameplay into a skill. Just input a simple idea, and you'll get both image generation prompts and video generation prompts directly. Now the prompts are taken care of. All you need to do is think about what kind of video you want to make. Great ideas are the most valuable!
Author @zhouluobo released a skill that automatically converts users' ideas into prompts for image and video generation, simplifying the FPV video creation process.
@VincentLogic: A widely recognized animation tool in the frontend community, 68K stars are no exaggeration! anime.js – a lightweight but incredibly powerful JavaScript animation engine. Frontend devs, you're in for a treat; it's like the Swiss Army knife for animators: all-rounder, whether it's CSS…
Anime.js is a lightweight yet powerful JavaScript animation engine that supports CSS, SVG, DOM attributes, and JavaScript object animation. It features an intuitive API, timeline system, scroll observer, drag-and-drop, and responsive animations. With 68K stars on GitHub, it's a go-to tool for frontend developers and interaction designers.
@FinanceYF5: This feels like magic! Someone made a short superpower clip with just one prompt: “Use telekinesis to make the TV seem to lift up—when you clench your fist, the TV gets crushed in midair” The pacing could be improved
Someone shared a short superpower clip generated from a single prompt on social media, showcasing the potential of AI video generation in creative content.